Modern neuroscience relies on integrating multi-scale, multimodal datasets to uncover the neural principles underlying intelligence. However, analytical challenges posed by highly heterogeneous data and fragmented workflows increasingly constrain discoveries. Here we introduce Se…
Clathrin-mediated endocytosis (CME) requires precise coordination between membrane deformation and force-generating protein assemblies, yet how these forces are dynamically organized in living cells remains poorly defined. Using multi-dimensional single particle tracking (SPT), w…
World Action Models (WAMs) model future environment evolution under action conditioning, offering a scalable paradigm for autonomous driving. However, existing approaches focus largely on model architecture design, and how a WAM can efficiently learn better world representations…